Muutke küpsiste eelistusi

E-raamat: Lung Imaging and Computer Aided Diagnosis

Edited by (University of Louisville, Kentucky, USA), Edited by (Global Biomedical Technologies, Inc., Roseville, USA)
  • Formaat: 496 pages
  • Ilmumisaeg: 19-Apr-2016
  • Kirjastus: CRC Press Inc
  • Keel: eng
  • ISBN-13: 9781040199343
Teised raamatud teemal:
  • Formaat - EPUB+DRM
  • Hind: 126,09 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Lisa ostukorvi
  • Lisa soovinimekirja
  • See e-raamat on mõeldud ainult isiklikuks kasutamiseks. E-raamatuid ei saa tagastada.
Lung Imaging and Computer Aided DiagnosisSuurem pilt
  • Formaat: 496 pages
  • Ilmumisaeg: 19-Apr-2016
  • Kirjastus: CRC Press Inc
  • Keel: eng
  • ISBN-13: 9781040199343
Teised raamatud teemal:

DRM piirangud

  • Kopeerimine (copy/paste):

    ei ole lubatud

  • Printimine:

    ei ole lubatud

  • Kasutamine:

    Digitaalõiguste kaitse (DRM)
    Kirjastus on väljastanud selle e-raamatu krüpteeritud kujul, mis tähendab, et selle lugemiseks peate installeerima spetsiaalse tarkvara. Samuti peate looma endale  Adobe ID Rohkem infot siin. E-raamatut saab lugeda 1 kasutaja ning alla laadida kuni 6'de seadmesse (kõik autoriseeritud sama Adobe ID-ga).

    Vajalik tarkvara
    Mobiilsetes seadmetes (telefon või tahvelarvuti) lugemiseks peate installeerima selle tasuta rakenduse: PocketBook Reader (iOS / Android)

    PC või Mac seadmes lugemiseks peate installima Adobe Digital Editionsi (Seeon tasuta rakendus spetsiaalselt e-raamatute lugemiseks. Seda ei tohi segamini ajada Adober Reader'iga, mis tõenäoliselt on juba teie arvutisse installeeritud )

    Seda e-raamatut ei saa lugeda Amazon Kindle's. 

Lung cancer remains the leading cause of cancer-related deaths worldwide. Early diagnosis can improve the effectiveness of treatment and increase a patients chances of survival. Thus, there is an urgent need for new technology to diagnose small, malignant lung nodules early as well as large nodules located away from large diameter airways because the current technologynamely, needle biopsy and bronchoscopyfail to diagnose those cases. However, the analysis of small, indeterminate lung masses is fraught with many technical difficulties. Often patients must be followed for years with serial CT scans in order to establish a diagnosis, but inter-scan variability, slice selection artifacts, differences in degree of inspiration, and scan angles can make comparing serial scans unreliable.

Lung Imaging and Computer Aided Diagnosis brings together researchers in pulmonary image analysis to present state-of-the-art image processing techniques for detecting and diagnosing lung cancer at an early stage. The book addresses variables and discrepancies in scans and proposes ways of evaluating small lung masses more consistently to allow for more accurate measurement of growth rates and analysis of shape and appearance of the detected lung nodules.

Dealing with all aspects of image analysis of the data, this book examines:





Lung segmentation Nodule segmentation Vessels segmentation Airways segmentation Lung registration Detection of lung nodules Diagnosis of detected lung nodules Shape and appearance analysis of lung nodules

Contributors also explore the effective use of these methodologies for diagnosis and therapy in clinical applications. Arguably the first book of its kind to address and evaluate image-based diagnostic approaches for the early diagnosis of lung cancer, Lung Imaging and Computer Aided Diagnosis constitutes a valuable resource for biomedical engineers, researchers, and clinicians in lung disease imaging.
Editors vii
Contributors ix
1 A Novel Three-Dimensional Framework for Automatic Lung Segmentation from Low-Dose Computed Tomography Images
1(16)
Ayman El-Baz
Georgy Gimel'farb
Robert Falk
Mohamed Abo El-Ghar
1.1 Introduction
1(1)
1.2 Joint Markov-Gibbs Model of LDCT Lung Images
2(7)
1.2.1 Spatial Interaction Model of LDCT Images
3(1)
1.2.2 Intensity Model of LDCT Lung Images
4(1)
1.2.2.1 Sequential EM-Based Initialization
5(1)
1.2.2.2 Modified EM Algorithm for LCDG
6(3)
1.3 Experimental Results and Validation
9(5)
1.4 Conclusions
14(3)
References
15(2)
2 Incremental Engineering of Lung Segmentation Systems
17(34)
Avishkar Misra
Arcot Sowmya
Paul Compton
2.1 Background
19(6)
2.1.1 Approaches to Medical Image Segmentation
19(1)
2.1.1.1 Classical Image Analysis
20(1)
2.1.1.2 Knowledge-Based or Syntactic Techniques
20(1)
2.1.1.3 Deformable Model Fitting
21(1)
2.1.1.4 Classification-Based Techniques
22(1)
2.1.1.5 Atlas-Based Segmentation via Registration
22(1)
2.1.2 Challenges to Segmenting Lungs in HRCT
23(1)
2.1.2.1 Interpatient and Intrapatient Variations
23(1)
2.1.2.2 Real and Artificial Artifacts
23(1)
2.1.2.3 Conflicting Ground Truth Definitions
24(1)
2.2 ProcessNet as a Network of Processes
25(2)
2.2.1 Internals of a Process
25(1)
2.2.2 Changes Affecting a Process
26(1)
2.3 ProcessNet Framework
27(5)
2.3.1 Ripple-Down Rules
28(1)
2.3.2 Detecting Process Change via Cornerstone Shift
29(1)
2.3.3 Managing Cornerstone Shifts
30(1)
2.3.4 Change Validation in a ProcessNet
31(1)
2.4 Lung Anatomy Segmentation Using ProcessNet
32(12)
2.4.1 Evaluation of ProcessNet in Operation
32(3)
2.4.2 Analysis of the PN9 Anatomy Segmentation System
35(5)
2.4.3 Quantitative Evaluation of Anatomy Segmentation
40(3)
2.4.4 Discussion
43(1)
2.5 Conclusions
44(7)
References
44(7)
3 3D MGRF-Based Appearance Modeling for Robust Segmentation of Pulmonary Nodules in 3D LDCT Chest Images
51(14)
Ayman El-Baz
Georgy Gimel'farb
Robert Falk
Mohamed Abo El-Ghar
3.1 Introduction
51(2)
3.1.1 Previous Work
52(1)
3.1.2 Basic Notation
52(1)
3.1.3 Our Model versus a Conventional Deformable Model
53(1)
3.2 Data Normalization
53(1)
3.3 MGRF-Based Prior Appearance Model
54(2)
3.3.1 Model Identification
54(2)
3.4 LCDG-Based Current Appearance Model
56(1)
3.5 Boundary Evolution Using Two Appearance Models
57(2)
3.6 Experimental Results
59(3)
3.7 Conclusions
62(3)
References
63(2)
4 Ground-Glass Nodule Characterization in High-Resolution Computed Tomography Scans
65(20)
Kazunori Okada
4.1 Introduction: Literature Review
65(4)
4.1.1 Radiographic Characteristics of GGNs
66(1)
4.1.2 Nomenclature of GGNs
66(1)
4.1.3 Clinical Prevalence: Epidemiology
66(1)
4.1.4 Malignancy of GGNs
66(1)
4.1.5 GGNs' Evolution and Histopathological Disease Progression
67(1)
4.1.6 Computer-Aided Detection and Diagnosis of GGNs
67(1)
4.1.7 Lung Nodule Volumetry and Its Limitation
68(1)
4.1.8 GGN Characterization: Our Approach
68(1)
4.2 Methods: RAGF Nodule Characterization
69(6)
4.2.1 Theory: Anisotropic Scale Space and Scale-Space Mean Shift
70(1)
4.2.2 Robust Gaussian Mean Estimation
71(1)
4.2.3 Robust Gaussian Covariance Estimation
71(1)
4.2.4 Robust Scale Selection
72(1)
4.2.5 Algorithm Overview
73(1)
4.2.6 Volumetric Measurements
73(2)
4.3 Experiments
75(2)
4.3.1 Data
75(1)
4.3.2 Results
75(2)
4.4 Conclusions
77(8)
Acknowledgments
80(1)
References
80(5)
5 Four-Dimensional Computed Tomography Lung Registration Methods
85(24)
Anand P. Santhanam
Yugang Min
Jannick P. Rolland
Celina Imielinska
Patrick A. Kupelian
5.1 Introduction
86(1)
5.2 CT Imaging Technology
87(3)
5.2.1 3DCT Imaging Technology
87(1)
5.2.2 4DCT Imaging Technology
88(1)
5.2.3 How Registration Helps in Knowing the Lung Motion
89(1)
5.3 Rigid-Body Transformations
90(2)
5.3.1 Automatic 3D Registration of Lung Surfaces in CT Scans
90(1)
5.3.2 Deformable 4DCT Lung Registration with Vessel Bifurcations
90(1)
5.3.3 Landmark Detection in the Chest and Registration of Lung Surfaces with an Application to Nodule Registration
91(1)
5.3.4 Modeling Respiratory Motion for Optimization of Lung Cancer Radiotherapy Using Fast MR Imaging and Intensity-Based Image Registration
91(1)
5.4 B-Splines and Thin-Plate Splines
92(2)
5.4.1 B-Splines
92(1)
5.4.1.1 Quantitative Assessment of Registration in Thoracic CT
92(1)
5.4.1.2 A Continuous 4D Motion Model from Multiple Respiratory Cycles for Use in Lung Radiotherapy
93(1)
5.4.2 TPS
93(1)
5.4.2.1 4DCT Image-Based Lung Motion Field Extraction and Analysis
93(1)
5.5 Physics-Based 3D Warping and Registration from Lung Images
94(1)
5.5.1 Noncompressibtlity
94(1)
5.5.2 Divergent Free
95(1)
5.5.3 Continuity Preserving
95(1)
5.6 Inverse Consistent Registration
95(2)
5.6.1 Consistent Landmark and Intensity-Based Image Registration
96(1)
5.6.2 Estimation of Regional Lung Expansion via 3D Image Registration
96(1)
5.6.3 Tracking Lung Tissue Motion and Expansion Compression with Inverse Consistent Image Registration and Spirometry
97(1)
5.7 Optical Flow-Based Methods
97(2)
5.7.1 Nonrigid Registration Method to Assess the Reproducibility of Breath-Holding with Active Breathing Control in Lung Cancer
98(1)
5.7.2 Evaluation of Deformable Registration of Patient Lung 4DCT with Subanatomical Region Segmentations
98(1)
5.8 Validation, the Much Needed Emphasis
99(2)
5.8.1 Deformable 4DCT Lung with Vessel Bifurcations
99(1)
5.8.2 Validation Using 3D Lung Phantom
99(1)
5.8.3 Validation Using Root Mean Square Error
99(1)
5.8.4 Validation Using Regression
100(1)
5.8.5 Validation and Comparison Methods for Free-Breathing 4D Lung CT
100(1)
5.9 Lung Radiotherapy
101(5)
5.9.1 Simulation and Visualization Requirements for Lung Radiotherapy
102(1)
5.9.2 Development of Physics-Based Deformable Lung Models from 4DCT Lung Registration
102(1)
5.9.2.1 Physics-Based 3D Deformable Lung Surface Model
102(1)
5.9.2.2 3D Lung Surface Deformations for PET/CT Image Registration
103(1)
5.9.2.3 Physics-Based Volumetric 3D Lung Model
103(1)
5.9.2.4 Application of Lung Deformation Estimated from 4DCT for Lung Radiotherapy Applications
104(2)
5.10 Conclusions
106(3)
Acknowledgments
106(1)
References
107(2)
6 Pulmonary Kinematics via Registration of Serial Lung Images
109(28)
Tessa Cook
Gang Song
Nicholas J. Tustison
Drew Torigian
Warren B. Gefter
James Gee
6.1 Introduction
109(2)
6.2 Estimating Pulmonary Motion via Serial Image Registration
111(6)
6.2.1 Elastic Matching of the Lung
112(1)
6.2.2 Diffeomorphic Image Registration
113(1)
6.2.2.1 Symmetric Normalization
114(1)
6.2.3 Image Similarity Functions
114(1)
6.2.3.1 Optical Flow and Demons Algorithm
114(1)
6.2.3.2 Normalized Cross-Correlation
115(1)
6.2.3.3 MI
116(1)
6.2.3.4 Other Similarity Metrics
116(1)
6.2.4 Numerical Implementation
116(1)
6.3 Quantifying Normal Lung Motion in Humans
117(4)
6.3.1 Quantification of Normal Human Lung Motion
119(2)
6.4 Evaluating Pathologic Lung Motion in Transgenic Mice
121(3)
6.4.1 Pathologic Lung Motion
122(2)
6.5 Evaluation of SyN in the EMPIRE10 Study
124(2)
6.5.1 Materials and Evaluation Protocol
125(1)
6.5.2 Results Using SyN
125(1)
6.6 Effects of Parameters on Motion Quantitation Accuracy
126(4)
6.6.1 Data Acquisition
126(1)
6.6.2 Experiment Setup
127(1)
6.6.3 Results
128(1)
6.6.3.1 Effect of Image Resolution
128(2)
6.6.3.2 Effect of Image Similarity Metrics
130(1)
6.7 Discussion
130(7)
References
131(6)
7 Acquisition and Automated Analysis of Normal and Pathological Lungs in Small Animals Using Microcomputed Tomography
137(14)
Xabier Artaechevarria
Mario Ceresa
Arrate Munoz-Barrutia
Carlos Ortiz-de-Solorzano
7.1 Introduction
137(1)
7.2 Image Acquisition
138(4)
7.2.1 Principles of Micro-CT
138(1)
7.2.2 In Vivo Imaging
139(2)
7.2.3 Ex Vivo Imaging
141(1)
7.3 Image Segmentation and Analysis
142(4)
7.3.1 Lung Parenchyma
142(1)
7.3.1.1 Normal Lungs and Diseases with Decreased Lung Density
142(2)
7.3.1.2 Diseases with Increased Lung Density
144(1)
7.3.2 Airways
144(1)
7.3.3 Pulmonary Vasculature
145(1)
7.3.3.1 Lung Function Imaging
146(1)
7.4 Discussion
146(5)
References
147(4)
8 Airway Segmentation and Analysis from Computed Tomography
151(38)
Benjamin Irving
Andrew Todd-Pokropek
Paul Taylor
8.1 Introduction
152(4)
8.1.1 Airway Anatomy
152(2)
8.1.2 CT Imaging of the Airways
154(1)
8.1.3 Pathology of the Airways
154(1)
8.1.3.1 Airway Deformation and Pulmonary Tuberculosis
154(1)
8.1.3.2 Congenital Cardiac Disease
155(1)
8.1.3.3 Lung Cancer
155(1)
8.1.3.4 Other Diseases of the Bronchi
155(1)
8.2 Segmentation
156(20)
8.2.1 Initialization
157(1)
8.2.2 Thresholding
158(1)
8.2.3 Thresholding with Topological Analysis
159(1)
8.2.3.1 Branch Validation Region-Growing
159(2)
8.2.3.2 Centerline-Based Improvement Technique
161(1)
8.2.4 Rule-Based Segmentation
162(2)
8.2.5 Fuzzy Segmentation
164(1)
8.2.5.1 Fuzzy Region Classification
164(2)
8.2.5.2 Fuzzy Connectivity
166(1)
8.2.6 Morphology
167(1)
8.2.6.1 Morphological Reconstruction
167(4)
8.2.6.2 Connection Cost and Energy Minimization
171(2)
8.2.7 Other Methods
173(1)
8.2.8 Airway Segmentation Evaluation (EXACTW Challenge)
173(1)
8.2.8.1 Methods
174(1)
8.2.8.2 Results and Discussion
174(2)
8.3 Analysis
176(9)
8.3.1 Skeletonization
176(1)
8.3.1.1 Region-Growing Methods
177(1)
8.3.1.2 Thinning Methods
178(1)
8.3.2 Anatomical Branch Labeling
179(3)
8.3.3 Branch Analysis
182(1)
8.3.4 Statistical Shape Models of Air way Trees
183(2)
8.4 Summary
185(4)
Acknowledgments
185(1)
References
185(4)
9 Pulmonary Vessel Segmentation for Multislice CT Data: Methods and Applications
189(32)
Jens N. Kaftan
Til Aach
9.1 Introduction
189(4)
9.1.1 Anatomy
190(1)
9.1.2 Vascular Diseases
190(1)
9.1.2.1 Pulmonary Embolism
191(2)
9.1.2.2 Pulmonary Hypertension
193(1)
9.2 Vessel Segmentation
193(17)
9.2.1 Intensity-Based Approaches
194(3)
9.2.2 Vessel Enhancement
197(2)
9.2.3 Vesselness-Based Approaches
199(2)
9.2.4 Fuzzy Segmentation
201(1)
9.2.4.1 Core Component Identification
202(2)
9.2.4.2 Fuzzy Vessel Segmentation
204(1)
9.2.4.3 Probability Function
205(3)
9.2.4.4 Centerline Extraction
208(1)
9.2.5 Artery-Vein Separation
208(2)
9.3 Applications
210(5)
9.3.1 PE-CAD
210(2)
9.3.2 Lung Nodule-CAD
212(1)
9.3.3 Airway Segmentation and Virtual Bronchoscopy
213(1)
9.3.4 Lung Fissures and Lung Registration
214(1)
9.4 Summary and Conclusions
215(6)
References
215(6)
10 A Novel Level Set-Based Computer-Aided Detection System for Automatic Detection of Lung Nodules in Low-Dose Chest Computed Tomography Scans
221(18)
Ayman El-Baz
Aly Farag
Georgy Gimel'farb
Robert Falk
Mohamed Abo El-Ghar
10.1 Introduction
221(2)
10.2 Methods and Data Acquisition
223(1)
10.3 Detecting Lung Nodules with Deformable Prototypes
224(4)
10.3.1 Deformable Prototype of a Candidate Nodule
224(2)
10.3.2 Similarity Measure for Grayscale Nodule Prototypes
226(1)
10.3.3 Lung Nodule Detection Algorithm
227(1)
10.4 Postclassification of Nodule Features
228(1)
10.5 Experimental Results and Conclusions
229(5)
10.6 Conclusions
234(5)
References
235(4)
11 Model-Based Methods for Detection of Pulmonary Nodules
239(28)
Paulo R. S. Mendonca
Rahul Bhotika
Robert Kaucic
11.1 Introduction
240(2)
11.1.1 State of the Art in CAD
241(1)
11.1.2 Overview
241(1)
11.1.3 Model-Based Approaches for Pulmonary Nodule Detection
241(1)
11.2 Region-Based Methods for Pulmonary Nodule Detection
242(5)
11.2.1 Signal Models
243(1)
11.2.2 Shape Models
243(2)
11.2.3 Anatomical Models
245(1)
11.2.4 Model Selection
246(1)
11.3 Voxel-Based Methods for Pulmonary Nodule Detection
247(11)
11.3.1 Differential Operators on Volume Images
247(1)
11.3.1.1 The Curvature Tensor
247(1)
11.3.1.2 The Voxel-Labeling Problem from a Bayesian Perspective
248(1)
11.3.1.3 Modeling the Likelihood Term
249(1)
11.3.1.4 Modeling the Prior
249(1)
11.3.1.5 Overview of the Modeling Procedure
250(1)
11.3.2 The Nodule Model
251(1)
11.3.2.1 Design of the Priors for the Nodule Model
252(1)
11.3.2.2 Derivation of the Likelihood
253(1)
11.3.2.3 Marginalization Over the Model Parameters
253(1)
11.3.3 The Vessel Model
254(1)
11.3.3.1 Design of the Priors for the Vessel Model
254(1)
11.3.3.2 Derivation of the Likelihood
255(1)
11.3.3.3 Marginalization Over the Model Parameters
255(1)
11.3.4 The Vessel Junction Model
256(1)
11.3.5 The Parenchyma Model
257(1)
11.4 Experimental Results
258(4)
11.4.1 Region-Based Methods
258(1)
11.4.2 Bayesian Voxel Labeling
259(3)
11.5 Summary and Conclusion
262(5)
Acknowledgments
263(1)
References
263(4)
12 Concept and Practice of Genetic Algorithm Template Matching and Higher Order Local Autocorrelation Schemes in Automated Detection of Lung Nodules
267(30)
Yongbum Lee
Takeshi Hara
DuYih Tsai
Hiroshi Fujita
12.1 Introduction
267(1)
12.2 TM Using a Genetic Algorithm
268(21)
12.2.1 TM
268(1)
12.2.2 Genetic Algorithms
269(3)
12.2.3 GATM
272(1)
12.2.3.1 Structure of GATM
272(1)
12.2.3.2 Setup of Simulation Studies Investigating GATM
273(1)
12.2.3.3 Results of the First Simulation Study Using GATM
274(7)
12.2.3.4 Results of the Second Simulation Study Using GATM
281(1)
12.2.3.5 Results of the Third Simulation Study Using GATM
282(1)
12.2.4 Nodule Detection by GATM in Chest Radiographs
283(2)
12.2.5 Nodule Detection by GATM in Thoracic CT Images
285(4)
12.3 HLAC with Multiple Regression
289(5)
12.3.1 HLAC
289(1)
12.3.2 Multiple Regression
290(1)
12.3.3 Pattern Recognition Using HLAC with Multiple Regression
291(1)
12.3.4 Nodule Detection Using HLAC in Thoracic CT Images
292(2)
12.4 Summary
294(3)
References
294(3)
13 Computer-Aided Detection of Lung Nodules in Chest Radiographs and Thoracic CT
297(26)
Kenji Suzuki
13.1 Introduction
297(2)
13.2 Databases
299(2)
13.2.1 Database of Low-Dose CT Images
299(2)
13.2.2 Database of Chest Radiographs
301(1)
13.3 CAD Scheme for Thoracic CT
301(5)
13.3.1 Current Scheme for Lung Nodule Detection in Low-Dose CT
301(1)
13.3.2 Architecture of Massive Training ANNs for FP Reduction
302(2)
13.3.3 Training Method of Expert MTANNs
304(1)
13.3.4 Scoring Method for Combining Output Pixels
305(1)
13.3.5 Mixing ANN for Combining Expert MTANNs
306(1)
13.4 CAD Scheme for Chest Radiographs
306(1)
13.4.1 Our CAD Scheme
306(1)
13.4.2 Preprocessing for Massive Training ANN FP Reduction
307(1)
13.5 Results
307(8)
13.5.1 Results for Thoracic CT
307(5)
13.5.2 Results for Chest Radiographs
312(3)
13.6 Discussion
315(2)
13.6.1 Thoracic CT CAD
315(2)
13.6.2 Chest Radiography CAD
317(1)
13.7 Conclusion
317(6)
Acknowledgments
317(1)
References
318(5)
14 Lung Nodule and Tumor Detection and Segmentation
323(20)
Jinghao Zhou
Dimitris N. Metaxas
14.1 Detection and Segmentation of GGO Nodule
324(8)
14.1.1 Introduction
324(1)
14.1.2 Methods
325(1)
14.1.2.1 Threshold for Lung Area Segmentation
325(1)
14.1.2.2 Vessel and Noise Suppression with 3D Cylinder Filters
325(1)
14.1.2.3 Detection of GGO
325(2)
14.1.2.4 Segmentation of GGO Using Nonparametric Density Estimation
327(1)
14.1.2.5 Removal Vessels Overlapped with Lung Abnormalities
328(1)
14.1.3 Results
329(1)
14.1.3.1 Results of GGO Detection
329(1)
14.1.4 Conclusion
330(2)
14.2 Detection and Segmentation of Large Lung Cancer
332(11)
14.2.1 Introduction
332(1)
14.2.2 Methods
333(1)
14.2.2.1 RASMs for Lung Area Segmentation
333(2)
14.2.2.2 Detection of Large Lung Cancers
335(1)
14.2.2.3 Segmentation of Large Lung Cancers
336(1)
14.2.3 Results
337(2)
14.2.4 Conclusion
339(1)
References
340(3)
15 Texture Classification in Pulmonary CT
343(26)
Lauge Sorensen
Mehrdad J. Gangeh
Saher B. Shaker
Marleen de Bruijne
15.1 Introduction
343(2)
15.2 Texture Descriptors
345(10)
15.2.1 Intensity Histogram
345(2)
15.2.2 Local Binary Patterns
347(2)
15.2.3 Gaussian Derivative-Based Filter Bank
349(1)
15.2.4 Gray-Level Co-Occurrence Matrices
350(1)
15.2.5 Gray-Level Run-Length Matrices
351(3)
15.2.6 Textons
354(1)
15.3 Evaluation
355(8)
15.3.1 A Case Study: Classification of Emphysema in CT
356(1)
15.3.2 Data
356(1)
15.3.3 Classification Setup
356(2)
15.3.4 Training and Parameter Selection
358(2)
15.3.5 Classification Results
360(1)
15.3.6 Selected Parameters
361(1)
15.3.7 Combining Information
362(1)
15.4 Discussion and Conclusion
363(6)
References
365(4)
16 Computer-Aided Assessment and Stenting of Tracheal Stenosis
369(26)
Romulo Pinho
Kurt G. Tournoy
Jan Sijbers
16.1 Introduction
369(1)
16.2 Clinical Background
370(3)
16.2.1 Anatomy of the Trachea
370(1)
16.2.2 Tracheal Stenosis
371(1)
16.2.3 Tracheal Stents
372(1)
16.3 Traditional Methods for Airway Assessment
373(3)
16.3.1 Rigid Bronchoscopy
373(1)
16.3.2 Flexible Bronchoscopy
374(2)
16.4 Computer-Aided Methods
376(14)
16.4.1 Manual Methods
376(3)
16.4.2 Semiautomatic Methods
379(3)
16.4.3 Deformable Models
382(1)
16.4.3.1 Estimation of Healthy Tracheas
382(4)
16.4.3.2 Segmentation of Narrowed Tracheas
386(2)
16.4.3.3 Quantification of Stenosis
388(1)
16.4.3.4 Choice of Stents
388(2)
16.5 Conclusions
390(5)
References
390(5)
17 Appearance Analysis for the Early Assessment of Detected Lung Nodules
395(10)
Ayman El-Baz
Georgy Gimel'farb
Robert Falk
Mohamed Abo El-Ghar
Jasjit Suri
17.1 Introduction
395(2)
17.1.1 Previous Work
396(1)
17.2 MGRF-Based Prior Appearance Model
397(2)
17.2.1 Neighborhood Selection
398(1)
17.3 Experimental Results
399(4)
17.4 Conclusions
403(2)
References
403(2)
18 Validation of a New Image-Based Approach for the Accurate Estimating of the Growth Rate of Detected Lung Nodules Using Real Computed Tomography Images and Elastic Phantoms Generated by State-of-the-Art Microfluidics Technology
405(16)
Ayman El-Baz
Palaniappan Sethu
Georgy Gimel'farb
Fahmi Khalifa
Ahmed Elnakib
Robert Falk
Mohamed Abo El-Ghar
Jasjit Suri
18.1 Introduction
405(3)
18.1.1 Previous Work
406(2)
18.2 Material and Methods
408(6)
18.2.1 Materials
408(1)
18.2.1.1 Elastic Phantoms
408(1)
18.2.1.2 In Vivo Data
409(1)
18.2.2 Methods
410(1)
18.2.2.1 Global Alignment
410(2)
18.2.2.2 Local Motion Model
412(2)
18.3 Results
414(2)
18.3.1 Validating the Proposed Approach on Elastic Phantoms
415(1)
18.3.2 Validation of the Proposed Registration on In Vivo Data
416(1)
18.4 Concluding Remarks
416(5)
References
419(2)
19 Three-Dimensional Shape Analysis Using Spherical Harmonics for Early Assessment of Detected Lung Nodules
421(18)
Ayman El-Baz
Matthew Nitzken
Georgy Gimel'farb
Eric Van Bogaert
Robert Falk
Mohamed Abo El-Ghar
Jasjit Suri
19.1 Introduction
421(4)
19.2 Methods
425(10)
19.2.1 Lung Nodules Segmentation
426(1)
19.2.1.1 Learning the Appearance Prior
427(1)
19.2.1.2 LCDG Models of Current Appearance
428(1)
19.2.1.3 Boundary Evolution under the Two Appearance Models
428(1)
19.2.2 Spherical Harmonic Shape Analysis
429(6)
19.2.3 Quantitative Lung Nodule Shape Analysis
435(1)
19.3 Experimental Results
435(1)
19.4 Conclusions
436(3)
References
436(3)
20 Review on Computer-Aided Detection, Diagnosis, and Characterization of Pulmonary Nodules: A Clinical Perspective
439(20)
Luca Saba
Jasjit Suri
20.1 Introduction
439(1)
20.2 Clinical Setting and Imaging Approach
440(3)
20.3 Management of the Pulmonary Nodule
443(1)
20.4 CAD Technology, Potential Application, and Application in Workflow
444(2)
20.5 CAD Sensitivity
446(1)
20.6 CAD Sensitivity Plus Radiologist
447(1)
20.7 Technical Parameters
448(5)
20.7.1 Nodule Dimension
448(1)
20.7.2 Section Thickness
449(1)
20.7.3 False Positive
449(3)
20.7.4 False Negative
452(1)
20.7.5 Nodule Position
452(1)
20.8 About Pulmonary Nodules Missed by Radiologists but Detected by CAD
453(1)
20.9 Contrast Material
453(1)
20.10 Reference Standard in the Evaluation of CAD Systems
453(1)
20.11 Consideration and Conclusion
454(5)
References
455(4)
Index 459
Ayman El-Baz received BSc and MS degrees in electrical engineering from Mansoura University, Egypt, in 1997 and 2000, respectively, and a PhD degree in electrical engineering from University of Louisville, Kentucky. He joined the Bioengineering Department of the University of Louisville in August 2006. His current research is focused on developing new computer-assisted diagnosis systems for different diseases and brain disorders.

Jasjit S. Suri is an innovator, a scientist, a visionary, an industrialist, and an internationally known world leader in biomedical engineering. Dr. Suri has spent over 20 years in the field of biomedical engineering/devices and its management. He received his doctorate from the University of Washington, Seattle, and a business management sciences degree from Weatherhead, Case Western Reserve University, Cleveland, Ohio. Dr. Suri was awarded the Presidents Gold Medal in 1980 and the Fellow of American Institute of Medical and Biological Engineering for his outstanding contributions.
Lisainfo e-raamatute kohta Lisainfo e-raamatute kohta
Püsilink: https://www.kriso.ee/db/97810401993436e.html
Märksõnad: